ExaMPI15: Workshop on Exascale MPI 2015
Monday November 16 2015
Hilton Salon F, Austin, TX, USA
Held in conjunction with SC15 (http://sc15.supercomputing.
Held in cooperation with ACM SIGHPC (http://www.sighpc.org/)
Hilton Salon F, Austin, TX, USA
Held in conjunction with SC15 (http://sc15.supercomputing.
Held in cooperation with ACM SIGHPC (http://www.sighpc.org/)
Workshop program
8.55 - 9.00 Welcome to the workshop
09.00 - 09.25 Practical Resilient Cases for FA-MPI, A Transactional Fault-Tolerant MPI Amin Hassani, Anthony Skjellum, Purushotham Bangalore and Ron Brightwell (Regular Paper)
09.25 - 10.00 Investigating MPI's Suitability for Highly Dynamic and Irregular Communication Pavan Balaji (Key-note talk)
10.00 - 10.30 Coffee Break
10.30 - 11.10 Programming models for Exascale: MPI+OpenMP and beyond Marc Snir (Key-note talk)
11.20 - 11.45 A Data Streaming Model in MPI Ivy Bo Peng, Stefano Markidis, Erwin Laure, Daniel Holmes and Mark Bull (Regular Paper)
11.45 - 12.00 Persistent Collective Operations in MPI Daniel Holmes, Anthony Skjellum, Matthew Shane Farmer and Purushotham Bangalore (Extended Abstract)
12.00 - 12.15 Fault Tolerance Assistant (FTA): An Exception Handling Approach for MPI Programs Aiman Fang, Ignacio Laguna, Kento Sato, Tanzima Islam and Kathryn Mohror (Extended Abstract)
12.15 - 12.30 Lightweight threading with MPI using Persistent Communications Semantics Ryan E. Grant, Anthony Skjellum and Purushotham V. Bangalore (Extended Abstract)
12.30 - 2.00 Lunch
2.00 - 2.35 Interconnect Hardware/Software Co-Design for Extreme-Scale Systems Ron Brightwell (Key-note talk)
2.35 - 3.00 Adaptive Transport Service Selection for MPI with InfiniBand Network Masamichi Takagi, Norio Yamaguchi, Balazs Gerofi, Atsushi Hori and Yutaka Ishikawa (Regular Paper)
3.00 - 3.30 Coffee Break
3.30 - 3.55 Overtime: A Tool for Analyzing Performance Variation due to Network Interference Ryan E. Grant, Kevin T. Pedretti and Ann Gentile (Regular Paper)
3.55 - 4.20 Preparing for Exascale: Modeling MPI for Many-Core Systems using Fine-Grain Queues Patrick Bridges, Matthew Dosanjh, Ryan E. Grant, Shane Farmer, Tony Skjellum and Ron Brightwell (Regular Paper)
4.20 - 4.35 Introducing Endpoints into the EMPI4Re MPI library Daniel Holmes (Extended Abstract)
4.35 - 4.50 Making the case for data staging coordination and control for parallel applications Florin Isaila and Jesus Carretero (Extended Abstract)
4.50 - 5.05 Characterization of Modern Numascale Cluster System with MPI Benchmarks Malik M Khan and Anne C. Elster (Extended Abstract)
5.05 - 5.10 Conclusions
Organizers
---------------
Stefano Markidis, KTH Royal Institute of Technology
Erwin Laure, KTH Royal Institute of Technology
William D. Gropp, University of Illinois at Urbana-Champaign
Jesper Larsson Träff, Technische Universität Wien
Masamichi Takagi, RIKEN AICS
Roberto Gioiosa, Pacific Northwest National Laboratory
Mirko Rahn, Fraunhofer Society
Mark Bull, Edinburgh Parallel Computing Centre
Daniel Holmes, Edinburgh Parallel Computing Centre
Contact
------------------------------
Stefano Markidis <markidis at kth.se>
8.55 - 9.00 Welcome to the workshop
09.00 - 09.25 Practical Resilient Cases for FA-MPI, A Transactional Fault-Tolerant MPI Amin Hassani, Anthony Skjellum, Purushotham Bangalore and Ron Brightwell (Regular Paper)
09.25 - 10.00 Investigating MPI's Suitability for Highly Dynamic and Irregular Communication Pavan Balaji (Key-note talk)
10.00 - 10.30 Coffee Break
10.30 - 11.10 Programming models for Exascale: MPI+OpenMP and beyond Marc Snir (Key-note talk)
11.20 - 11.45 A Data Streaming Model in MPI Ivy Bo Peng, Stefano Markidis, Erwin Laure, Daniel Holmes and Mark Bull (Regular Paper)
11.45 - 12.00 Persistent Collective Operations in MPI Daniel Holmes, Anthony Skjellum, Matthew Shane Farmer and Purushotham Bangalore (Extended Abstract)
12.00 - 12.15 Fault Tolerance Assistant (FTA): An Exception Handling Approach for MPI Programs Aiman Fang, Ignacio Laguna, Kento Sato, Tanzima Islam and Kathryn Mohror (Extended Abstract)
12.15 - 12.30 Lightweight threading with MPI using Persistent Communications Semantics Ryan E. Grant, Anthony Skjellum and Purushotham V. Bangalore (Extended Abstract)
12.30 - 2.00 Lunch
2.00 - 2.35 Interconnect Hardware/Software Co-Design for Extreme-Scale Systems Ron Brightwell (Key-note talk)
2.35 - 3.00 Adaptive Transport Service Selection for MPI with InfiniBand Network Masamichi Takagi, Norio Yamaguchi, Balazs Gerofi, Atsushi Hori and Yutaka Ishikawa (Regular Paper)
3.00 - 3.30 Coffee Break
3.30 - 3.55 Overtime: A Tool for Analyzing Performance Variation due to Network Interference Ryan E. Grant, Kevin T. Pedretti and Ann Gentile (Regular Paper)
3.55 - 4.20 Preparing for Exascale: Modeling MPI for Many-Core Systems using Fine-Grain Queues Patrick Bridges, Matthew Dosanjh, Ryan E. Grant, Shane Farmer, Tony Skjellum and Ron Brightwell (Regular Paper)
4.20 - 4.35 Introducing Endpoints into the EMPI4Re MPI library Daniel Holmes (Extended Abstract)
4.35 - 4.50 Making the case for data staging coordination and control for parallel applications Florin Isaila and Jesus Carretero (Extended Abstract)
4.50 - 5.05 Characterization of Modern Numascale Cluster System with MPI Benchmarks Malik M Khan and Anne C. Elster (Extended Abstract)
5.05 - 5.10 Conclusions
Organizers
---------------
Stefano Markidis, KTH Royal Institute of Technology
Erwin Laure, KTH Royal Institute of Technology
William D. Gropp, University of Illinois at Urbana-Champaign
Jesper Larsson Träff, Technische Universität Wien
Masamichi Takagi, RIKEN AICS
Roberto Gioiosa, Pacific Northwest National Laboratory
Mirko Rahn, Fraunhofer Society
Mark Bull, Edinburgh Parallel Computing Centre
Daniel Holmes, Edinburgh Parallel Computing Centre
Contact
------------------------------
Stefano Markidis <markidis at kth.se>
******************************
(
()
******************************
No comments:
Post a Comment